Over the 121.1 days, Google used 96 vCPUs, 1.4 TB of RAM, read 9.02 PB of data, and wrote 7.95 PB.
In honor of Pi Day on Thursday, March 14, Google announced that the company's own Emma Haruka Iwao has surpassed the world record pi computation by almost nine trillion digits. During the entire time it took for calculations, the Google Cloud server were kept switched on to avoid any interruptions. But since it's an irrational number, "there's no end to how many of its digits can be calculated". The Google employee and her team calculated 31,415,926,535,897 digits of pi - crushing a 2016 record by trillions of digits.
Iwao did her number crunching primarily from Google's office in Osaka, Japan, where she works at as a developer and advocate for Google Cloud. It's the number you get when you divide a circle's circumference by its diameter.
This feat was accomplished using y-cruncher and the Chudnovsky formula, the same program and algorithm that allowed Trueb and various other mathematicians to compute the previous world record calculations. It is significantly used in geometrical calculations.
According to Google, Iwao has been fascinated by pi since she was 12.
Facebook blames long outage on 'server configuration change'
And if you haven't rushed to Twitter yet , we'll save you the trouble: yes, Facebook posting is down and Instagram is buggy. The hashtag #FacebookDown and #InstagramDown were trending on Twitter for much of the day.
Pi Day, also known as Pie Approximation Day, is held every year on March 14 in honour of the mathematical constant Pi.
Talking about her journey, she says, "When I was a kid, I didn't have access to supercomputers. I was very fortunate that there were Japanese world record holders that I could relate to", Iwao said in the blog post.
'I'm really happy to be one of the few women in computer science holding the record, and I hope I can show more people who want to work in the industry what's possible'.
Typically, such calculations have been done on a single machine or "virtual machine" because of the difficulty for passing information back and forth over the network when using multiple machines working together.